居民个体出行行为聚类及出行模式分析* ——以三亚市为例
Individual Travel Behavior Clustering and Travel Pattern Analysis: A Case Study of Sanya
陈 仲
中国城市规划设计研究院 工程师，硕士
杨克青（通信作者）
华南理工大学 讲师，博士
摘要: 手机信令数据不仅记录个体出行轨迹，同时也为分析城市居民出行模式提供了基础。通过提出一种基于狄利克雷过程混合模型的聚类方法，以从手机信令提取的出行OD（Origin-Destination）为基础，研究个体出行行为及群体出行模式。与其他聚类方法相比，该方法最大的优点在于无需事先指定聚类的数量，并且能够基于数据识别出新的聚类。通过将该方法应用到三亚市的居民出行行为研究中，得到15类个体行为聚类。从而进一步结合城市特征，归纳得出5种典型出行模式，较为全面地反映三亚居民活动的实际情况，为制定差异化的交通政策、精细化交通管理提供支撑。
Abstract: The mobile phone data not only records the individual travel trajectory, but also provides a basis for analyzing the travel patterns of urban residents. This paper proposes a clustering method based on the Dirichlet Process Mixture Model. Based on the trip OD （Origin-Destination）extracted from the mobile phone data, this paper studies individual travel behavior and residents' travel pattern. Compared with other clustering methods, the biggest advantage of this method is that there is no need to specify the number of clusters in advance, and new clusters can be identified based on the data. This paper applies this method to Sanya, and 15 types of individual behavior clusters are obtained. Based on the characteristics of the city, five typical travel patterns are summarized, which more comprehensively reflect the actual situation of residents' activities in Sanya, and provide support for the formulation of differentiated traffic policies and refined traffic management.
关键词：出行行为；模式聚类；手机信令；狄利克雷混合模型
Keyword: travel behavior; mode clustering; mobile phone data; Dirichlet Process Mixture Model
中图分类号：TU984
文献标识码: A
资金资助
广东省软科学研究计划项目 “有效利用信息科技提高城市凝聚力——构建‘城市新移民信息选择与社会认同’传播模型” 2016A070706003
SONG C, KOREN T, WANG P, et al. Modeling the scaling properties of human mobility[J]. Nature Physics, 2010, 6: 818-823.
冯建喜，杨振山. 南京市城市老年人出行行为的影响因素[J]. 地理科学进展，2015，34（12）：1598-1608.
FENG Jianxi, YANG Zhenshan. Factors influencing travel behavior of urban elderly people in Nanjing[J]. Progress in Geography, 2015, 34(12): 1598-1608.
曹小曙，林强. 基于结构方程模型的广州城市社区居民出行行为[J]. 地理学报，2011，66（2）：167-177.
CAO Xiaoshu, LIN Qiang. A SEM-based study on urban community resident's travel behavior in Guangzhou[J]. Acta Geographica Sinica, 2011, 66(2): 167-177.
石天戈，张小雷，杜宏茹，等. 乌鲁木齐市居民出行行为的空间特征和碳排放分析[J]. 地理科学进展，2013，32（6）：897-905.
SHI Tiange, ZHANG Xiaolei, DU Hongru, et al. Spatial characteristics of residents' outings and carbon emissions in Urumqi City[J]. Progress in Geography, 2013, 32(6): 897-905.
钮心毅，丁亮，宋小冬. 基于职住空间关系分析上海郊区新城发展状况[J]. 城市规划，2017，41（8）：47-53，126.
NIU Xinyi, DING Liang, SONG Xiaodong. Analyzing suburban new town development in Shanghai from the perspective of jobs-housing spatial relationship[J]. City Planning Review, 2017, 41(8): 47-53, 126.
钮心毅，丁亮，宋小冬. 基于手机数据识别上海中心城的城市空间结构[J]. 城市规划学刊，2014（6）：61-67.
NIU Xinyi, DING Liang, SONG Xiaodong. Understanding urban spatial structure of Shanghai central city based on mobile phone data[J]. Urban Planning Forum, 2014(6): 61-67.
丁亮，钮心毅，宋小冬. 上海中心城就业中心体系测度——基于手机信令数据的研究[J].地理学报，2016，71（3）：484-499.
DING Liang, NIU Xinyi, SONG Xiaodong. Measuring the employment center system in Shanghai central city: a study using mobile phone signaling data[J]. Acta Geographica Sinica, 2016, 71(3): 484-499.
申卓，王德. 基于手机信令数据的大型足球赛事球迷当日空间行为特征研究[J]. 人文地理，2018，33（3）：34-43.
SHEN Zhuo, WANG De. A research on the spatial behavior characteristics of fans of large football matches based on cell phone signaling data[J]. Human Geography, 2018, 33(3): 34-43.
方家，王德，谢栋灿，等. 上海顾村公园樱花节大客流特征及预警研究——基于手机信令数据的探索[J]. 城市规划，2016，40（6）：43-51.
FANG Jia, WANG De, XIE Dongcan, et al. Research on dynamic change and early warning of large tourist flow based on mobile signal data analysis: a case study of Gucun Park Sakura Festival in Shanghai[J]. City Planning Review, 2016, 40(6): 43-51.
龙奋杰，石朗，彭智育，等. 基于手机信令数据的城市公园服务评价[J]. 城市问题，2018（6）：88-92.
LONG Fenjie, SHI Lang, PENG Zhiyu, et al. Service evaluation of city park using cell phone signaling data[J]. Urban Problems, 2018(6): 88-92.
姚海芳，冯天楠，刘劲松. 基于手机信令数据的机场航空旅客分类识别研究——以石家庄正定国际机场为例[J]. 地理与地理信息科学，2020，36（3）：56-62.
YAO Haifang, FENG Tiannan, LIU Jinsong. Air passenger classification based on mobile phone signaling data: a case study of the Shijiazhuang Zhengding International Airport[J]. Geography and Geo-information Science, 2020, 36(3): 56-62.
IQBAL M S, CHOUDHURY C F, WANG P, et al. Development of origin–destination matrices using mobile phone call data[J]. Transportation Research Part C Emerging Technologies, 2014, 40: 63-74.
GERSHMAN S J, BLEI D M. A tutorial on Bayesian nonparametric models[J]. Journal of Mathematical Psychology, 2012, 56(1): 1-12.
